gemini-cli - 💡(How to fix) Fix 403 PERMISSION_DENIED after signing in with Google OAuth [3 comments, 4 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
google-gemini/gemini-cli#26080Fetched 2026-04-28 06:49:44
View on GitHub
Comments
3
Participants
4
Timeline
10
Reactions
1
Timeline (top)
commented ×3mentioned ×3subscribed ×3labeled ×1
RAW_BUFFERClick to expand / collapse

What happened?

I am unable to use Gemini CLI after signing in with Google OAuth.

The CLI shows that I am signed in and detects my tier correctly, but every prompt fails with:

403 PERMISSION_DENIED The caller does not have permission

The request appears to fail against: cloudcode-pa.googleapis.com/v1internal:streamGenerateContent?alt=sse

This looks like a backend entitlement / permission issue rather than a local configuration problem.

What did you expect to happen?

After signing in with Google OAuth, Gemini CLI should be able to send prompts and receive responses normally.

At minimum, gemini-2.5-flash should work without returning 403 PERMISSION_DENIED.

Client information

<details> <summary>Client Information</summary>

CLI Version: 0.39.1 Git Commit: 4d73f3413 Model: Auto (Gemini 3) Sandbox: no sandbox OS: android Auth Method: Signed in with Google ([email protected]) Tier: Gemini Code Assist in Google One AI Pro

</details>

Login information

I am logging in with Google OAuth using [email protected].

I am not using an API key or Vertex AI for this test.

Anything else we need to know?

This seems to be a backend permission / entitlement issue.

The CLI correctly shows my Google account and tier, but all generation requests fail with 403 PERMISSION_DENIED.

If helpful, I can provide the x-cloudai-companion-trace-id from the debug console.

extent analysis

TL;DR

The issue is likely due to a backend permission or entitlement issue, and verifying the user's tier and permissions may help resolve the 403 PERMISSION_DENIED error.

Guidance

  • Check the user's tier and permissions to ensure they match the required entitlements for the Gemini CLI to function correctly.
  • Verify that the Google OAuth authentication is correctly configured and that the user's account is properly linked to the Gemini service.
  • Consider providing the x-cloudai-companion-trace-id from the debug console for further investigation into the permission issue.
  • Review the Gemini CLI documentation to ensure that the user is using the correct version and configuration for their tier and permissions.

Notes

The issue seems to be related to a backend permission or entitlement issue, rather than a local configuration problem. The user's tier and permissions may need to be adjusted or verified to resolve the issue.

Recommendation

Apply workaround: Verify the user's tier and permissions to ensure they match the required entitlements for the Gemini CLI to function correctly, as this is likely the root cause of the 403 PERMISSION_DENIED error.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING